Application of neural waveform predistortion to experimental TWT data

Author

Bernardini, A. ; De Fina, S.

Author_Institution

Rome Univ., Italy

fYear

1991

Firstpage

468

Abstract

An evaluation is made of the predistorter´s achievable performance using HPA (high-power amplifier) models matched to experimental TWT data. How the neural net capability for inverse modeling, and then as predistorter, is related to the various TWTs that must be fitted is discussed. A supervised neural net is used with one internal neuron and no more than 10 internal unit, and the backpropagation algorithm for the learning process. The results related to TWT data obtained confirm the performances achievable with the generic TWT model: an average gain of 3 dB for the 64-QAM and an average gain of 5.5 dB for the 256-QAM systems, with respect to a baseband predistorter

Keywords

amplitude modulation; microwave amplifiers; neural nets; power amplifiers; signal processing; travelling-wave-tubes; 256-QAM; 3.0 dB; 5.5 dB; 64-QAM; average gain; backpropagation algorithm; baseband predistorter; experimental TWT data; high-power amplifier; internal unit; inverse modeling; learning process; neural net; neural waveform predistortion; performances; supervised neural net; Inverse problems; Neural networks; Neurons; Performance analysis; Performance gain; Predistortion; Proposals; Quadrature amplitude modulation; Radio transmitters; Signal processing algorithms;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrotechnical Conference, 1991. Proceedings., 6th Mediterranean

Conference_Location

LJubljana

Print_ISBN

0-87942-655-1

Type

conf

DOI

10.1109/MELCON.1991.161878

Filename

161878